Performance of Machine Learning-Based Multi-Model Voting Ensemble Methods for Network Threat Detection in Agriculture 4.0.

Nikolaos Peppes,Theodoros Alexakis,Evgenia Adamopoulou,Emmanouil Daskalakis,Konstantinos Demestichas

doi:10.3390/s21227475

Abstract

The upcoming agricultural revolution, known as Agriculture 4.0, integrates cutting-edge Information and Communication Technologies in existing operations. Various cyber threats related to the aforementioned integration have attracted increasing interest from security researchers. Network traffic analysis and classification based on Machine Learning (ML) methodologies can play a vital role in tackling such threats. Towards this direction, this research work presents and evaluates different ML classifiers for network traffic classification, i.e., K-Nearest Neighbors (KNN), Support Vector Classification (SVC), Decision Tree (DT), Random Forest (RF) and Stochastic Gradient Descent (SGD), as well as a hard voting and a soft voting ensemble model of these classifiers. In the context of this research work, three variations of the NSL-KDD dataset were utilized, i.e., initial dataset, undersampled dataset and oversampled dataset. The performance of the individual ML algorithms was evaluated in all three dataset variations and was compared to the performance of the voting ensemble methods. In most cases, both the hard and the soft voting models were found to perform better in terms of accuracy compared to the individual models.

Highlights

IntroductionPublisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations
The third objective of this paper is to suggest a new line for research works, which evaluates ensemble models of different sets of Machine Learning (ML) network traffic classifiers on various datasets suitable for Agriculture 4.0 applications
The goal of this study was to present a comparative analysis of the performance of five different ML classifiers when they are applied individually, as well as when they are part of hard and soft voting ensemble methods

Summary

Introduction

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. Agriculture evolves at a rapid pace nowadays, transitioning into a new era known as Agriculture 4.0. Considering the challenges of modern agriculture (e.g., climate change, diseases, excessive use of chemicals and resources, etc.), Agriculture 4.0 aims to engage new technologies and methods in order to alleviate the existing challenges, reduce the risks and lead to more efficient and safer production. To this end, it engages a plethora of advanced Information and Communication Technologies (ICTs) [1]

Objectives

Results

Conclusion